Work

Complex-Valued DNN for Broadband Dielectric Characterization of Dispersive Lossy Materials

Year: 2024

Type: conference-paper

Abstract: This paper presents a broadband dielectric characterization method based on a Complex-Valued Deep Neural Network (CVNN) that allows the retrieval of permittivity and conductivity of dispersive lossy materials using ad-hoc setups. To validate the method, we numerically tested it employing a partially filled custom-made double-ridge waveguide setup, working from 0.95 to 4.2GHz. Moreover, we include a feature importance analysis using agnostic explainable-AI (XAI) techniques. The results demonstrate the flexibility and the retrieval capabilities of the method, as well as the advantages and drawbacks in comparison with traditional techniques. We publicly release the dataset and codes to support further research.

Source: IEEE Latin American Conference on Antennas and Propagation (LACAP)

DOI: 10.1109/lacap63752.2024.10876315

Authors: Nuwan Bandara, Martina Gugliermino, Mauro Lumia, Giuseppe Virone, Francesca Vipiana, David Orlando Rodriguez-Duarte

Institutions: Singapore Management University, Politecnico di Torino, Institute of Electronics, Computer and Telecommunication Engineering, National Research Council

Language: English

Topic: Microwave and Dielectric Measurement Techniques

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4407628437

FWCI:

Cites: 5

Cited by:

Related to: 10